INDEX

Explanations

inquiries and requests for answers to questions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

allah

-0.15

ahat

-0.14

 Axel

-0.14

Erd

-0.14

ADI

-0.14

avel

-0.14

Artifact

-0.14

 Alejandro

-0.14

dig

-0.14

aving

-0.14

POSITIVE LOGITS

 answer

0.73

 answers

0.68

 Answer

0.64

answer

0.63

Answer

0.58

 ANSW

0.57

ans

0.57

 answered

0.55

.answer

0.55

Ans

0.55

Activations Density 0.111%

inquiries and requests for answers to questions

No Comments

No Known Activations